kavg commited on
Commit
744f418
1 Parent(s): c8981a2

LiLT-RE-PT-SIN

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: kavg/LiLT-RE-PT
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - xfun
8
+ metrics:
9
+ - precision
10
+ - recall
11
+ - f1
12
+ model-index:
13
+ - name: checkpoints
14
+ results: []
15
+ ---
16
+
17
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
18
+ should probably proofread and complete it, then remove this comment. -->
19
+
20
+ # checkpoints
21
+
22
+ This model is a fine-tuned version of [kavg/LiLT-RE-PT](https://huggingface.co/kavg/LiLT-RE-PT) on the xfun dataset.
23
+ It achieves the following results on the evaluation set:
24
+ - Precision: 0.3631
25
+ - Recall: 0.4823
26
+ - F1: 0.4143
27
+ - Loss: 0.1671
28
+
29
+ ## Model description
30
+
31
+ More information needed
32
+
33
+ ## Intended uses & limitations
34
+
35
+ More information needed
36
+
37
+ ## Training and evaluation data
38
+
39
+ More information needed
40
+
41
+ ## Training procedure
42
+
43
+ ### Training hyperparameters
44
+
45
+ The following hyperparameters were used during training:
46
+ - learning_rate: 1e-05
47
+ - train_batch_size: 8
48
+ - eval_batch_size: 2
49
+ - seed: 42
50
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
+ - lr_scheduler_type: linear
52
+ - lr_scheduler_warmup_ratio: 0.1
53
+ - training_steps: 10000
54
+
55
+ ### Training results
56
+
57
+ | Training Loss | Epoch | Step | Precision | Recall | F1 | Validation Loss |
58
+ |:-------------:|:------:|:-----:|:---------:|:------:|:------:|:---------------:|
59
+ | 0.0907 | 41.67 | 500 | 0.3315 | 0.3106 | 0.3207 | 0.2039 |
60
+ | 0.0766 | 83.33 | 1000 | 0.3631 | 0.4823 | 0.4143 | 0.1671 |
61
+ | 0.0639 | 125.0 | 1500 | 0.3640 | 0.6086 | 0.4556 | 0.2525 |
62
+ | 0.0309 | 166.67 | 2000 | 0.3973 | 0.6010 | 0.4784 | 0.2339 |
63
+ | 0.0318 | 208.33 | 2500 | 0.4045 | 0.6414 | 0.4961 | 0.3325 |
64
+ | 0.0144 | 250.0 | 3000 | 0.4268 | 0.6187 | 0.5052 | 0.3513 |
65
+ | 0.0163 | 291.67 | 3500 | 0.4273 | 0.6086 | 0.5021 | 0.2880 |
66
+ | 0.0062 | 333.33 | 4000 | 0.4368 | 0.6288 | 0.5155 | 0.3064 |
67
+ | 0.0115 | 375.0 | 4500 | 0.4386 | 0.6313 | 0.5176 | 0.3283 |
68
+ | 0.0168 | 416.67 | 5000 | 0.4373 | 0.6162 | 0.5115 | 0.3258 |
69
+ | 0.0062 | 458.33 | 5500 | 0.4530 | 0.6086 | 0.5194 | 0.3467 |
70
+ | 0.0074 | 500.0 | 6000 | 0.4569 | 0.6162 | 0.5247 | 0.3401 |
71
+ | 0.0037 | 541.67 | 6500 | 0.4559 | 0.6136 | 0.5231 | 0.3526 |
72
+ | 0.008 | 583.33 | 7000 | 0.4650 | 0.6035 | 0.5253 | 0.3076 |
73
+ | 0.0045 | 625.0 | 7500 | 0.4610 | 0.6111 | 0.5255 | 0.3799 |
74
+ | 0.0045 | 666.67 | 8000 | 0.4551 | 0.6136 | 0.5226 | 0.3692 |
75
+ | 0.0052 | 708.33 | 8500 | 0.4535 | 0.6162 | 0.5225 | 0.3492 |
76
+ | 0.0002 | 750.0 | 9000 | 0.4537 | 0.6061 | 0.5189 | 0.4075 |
77
+ | 0.0027 | 791.67 | 9500 | 0.4581 | 0.6212 | 0.5273 | 0.3816 |
78
+ | 0.0009 | 833.33 | 10000 | 0.4569 | 0.6162 | 0.5247 | 0.3834 |
79
+
80
+
81
+ ### Framework versions
82
+
83
+ - Transformers 4.38.2
84
+ - Pytorch 2.1.0+cu121
85
+ - Datasets 2.18.0
86
+ - Tokenizers 0.15.1
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "kavg/LiLT-RE-PT",
3
+ "architectures": [
4
+ "LiLTRobertaLikeForRelationExtraction"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "channel_shrink_ratio": 4,
9
+ "classifier_dropout": null,
10
+ "eos_token_id": 2,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 3072,
16
+ "layer_norm_eps": 1e-05,
17
+ "max_2d_position_embeddings": 1024,
18
+ "max_position_embeddings": 514,
19
+ "model_type": "lilt",
20
+ "num_attention_heads": 12,
21
+ "num_hidden_layers": 12,
22
+ "output_past": true,
23
+ "pad_token_id": 1,
24
+ "position_embedding_type": "absolute",
25
+ "torch_dtype": "float32",
26
+ "transformers_version": "4.38.2",
27
+ "type_vocab_size": 1,
28
+ "use_cache": true,
29
+ "vocab_size": 250002
30
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42ea5c9f4d20eb639313019ff66842c714d9b6523b776a5c30837fb5f7d76166
3
+ size 1147300280
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f59925fcb90c92b894cb93e51bb9b4a6105c5c249fe54ce1c704420ac39b81af
3
+ size 17082756
tokenizer_config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "250001": {
36
+ "content": "<mask>",
37
+ "lstrip": true,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "<s>",
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "<s>",
47
+ "eos_token": "</s>",
48
+ "mask_token": "<mask>",
49
+ "model_max_length": 512,
50
+ "pad_token": "<pad>",
51
+ "sep_token": "</s>",
52
+ "tokenizer_class": "XLMRobertaTokenizer",
53
+ "unk_token": "<unk>"
54
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cefea6284d8fd126731da6372c68392d0a31ffe1db15409e37e4862b500f3dde
3
+ size 5048